Intelligent radiation source identification method based on ensemble learning
The invention discloses an intelligent radiation source identification method based on integrated learning, and the method comprises the following steps: S1, carrying out the data enhancement through the integrated learning, and obtaining the enhanced data; s2, according to the enhanced data, adopti...
Gespeichert in:
Hauptverfasser: | , , , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses an intelligent radiation source identification method based on integrated learning, and the method comprises the following steps: S1, carrying out the data enhancement through the integrated learning, and obtaining the enhanced data; s2, according to the enhanced data, adopting the trained known target classification network to identify an unknown target; s3, calibrating an unknown target, and updating the classification network; and S4, carrying out reentry identification on an unknown target by adopting the updated classification network to obtain a radiation source identification result. According to the method, the sample utilization rate is improved, the purpose of data enhancement is achieved under the condition of small samples, the unknown electromagnetic target can be better identified, the classification network is retrained through the identified unknown target, reentry identification is carried out, timely updating of the classification network is guaranteed, and the identi |
---|